Article record

MambaGLA-NPC：一种集成CNN和状态空间模型的三维框架，用于稳健的多中心鼻咽癌分割

MambaGLA-NPC: a 3D framework integrating CNN and state space models for robust multi-center nasopharyngeal carcinoma segmentation.

AI/ML鼻咽癌IF 6.1Q1

文献信息

PMID	42871411
原文	在 PubMed 查看原文 ↗
发表日期	2026
作者	Wei Jin 查看其他 4 位作者 Xiaobo Chen；Weifeng Jin；Hai Liao；Li Yu
作者单位	School of Artificial Intelligence for Traditional Chinese Medicine, Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China. 查看其他 5 条单位信息 Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, Guangdong, China.；Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, Guangdong, China.；School of Pharmaceutical Sciences, Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China.；Department of Medical Imaging Center, Guangxi Medical University Cancer Hospital, Guangxi Clinical Research Center for Medical Imaging Construction, Guangxi Key Clinical Specialty (Medical Imaging Department), Dominant Cultivation Discipline of Guangxi Medical University Cancer Hospital (Medical Imaging Department), Nanning, China.；School of Basic Medical Sciences, Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China.
期刊	Frontiers in genome editing
SCI 分区	Q1
IF	6.1
研究类型	AI/ML · 临床
所属专科	鼻咽癌

中文摘要

背景与目的： 从MRI中准确进行鼻咽癌（NPC）的三维分割对于放疗计划至关重要，但由于多中心泛化性差、缺乏空间连续性以及全局建模的高计算成本，仍然具有挑战性。我们旨在通过提出一种新颖的三维框架来解决这些局限性。
方法： 我们提出了MambaGLA-NPC，一种三维深度学习框架，在U形编码器-解码器架构中集成了状态空间模型（SSMs）和卷积神经网络（CNNs）。Conv-GLSSM模块通过卷积联合提取静态局部特征，并通过具有三维局部扫描策略的SSMs提取全局上下文。门控通道-空间注意力（GCS Att）模块抑制跳跃连接中的无关噪声，而NPC特异性适配器能够跨多中心数据集进行参数高效的微调。
结果： 在来自三家医院的1,098名NPC患者的多中心数据集上，我们的模型在内部测试集上达到了最先进的性能（Dice：80.47%，IoU：67.83%，HD95：4.09 mm）。在跨中心评估中，它显著优于先前方法（例如，在两个外部中心上的Dice分别为87.13%和76.70%）。与无适配相比，NPC-Adapter将跨中心Dice提升了高达8.84%。消融研究证实了每个模块的贡献，并且Conv-GLSSM相比Transformers降低了计算成本（21.66 GFLOPs vs. 在128^3分辨率下自注意力的OOM）。
结论： MambaGLA-NPC是首个基于Mamba的三维NPC分割框架，有效平衡了局部-全局特征集成与线性复杂度，在多中心MRI数据上实现了优越的准确性和泛化性，同时保持了高效率。

英文摘要

BACKGROUND AND OBJECTIVE: Accurate 3D segmentation of nasopharyngeal carcinoma (NPC) from MRI is critical for radiotherapy planning but remains challenging due to poor multi-center generalization, lack of spatial continuity, and high computational costs of global modeling. We aim to address these limitations by proposing a novel 3D framework.
METHODS: We propose MambaGLA-NPC, a 3D deep learning framework integrating State Space Models (SSMs) and Convolutional Neural Networks (CNNs) in a U-shaped encoder-decoder architecture. A Conv-GLSSM module jointly extracts static local features via convolutions and global context via SSMs with a 3D local scanning strategy. A gated channel-spatial attention (GCS Att) module suppresses irrelevant noise in skip connections, and an NPC-specific adapter enables parameter-efficient fine-tuning across multi-center datasets.
RESULTS: On a multi-center dataset of 1,098 NPC patients from three hospitals, our model achieves state-of-the-art performance on the internal test set (Dice: 80.47%, IoU: 67.83%, HD95: 4.09 mm). Under cross-center evaluation, it significantly outperforms prior methods (e.g., Dice of 87.13% and 76.70% on two external centers). The NPC-Adapter boosts cross-center Dice by up to 8.84% compared to no adaptation. Ablation studies confirm the contribution of each module, and the Conv-GLSSM reduces computational cost versus Transformers (21.66 GFLOPs vs. OOM for self-attention at 128 3 resolution).
CONCLUSION: MambaGLA-NPC is the first Mamba-based 3D NPC segmentation framework that effectively balances local-global feature integration with linear complexity, achieving superior accuracy and generalization across multi-center MRI data while maintaining high efficiency.